Question

Consider following statements :
A. Regression predicts categorical outcomes.

B. Classification models are used for continuous variable prediction.

C. Clustering is an unsupervised learning task.

D. Reinforcement learning uses rewards and penalties to improve performance.

E. Decision tree can be used for both classification and regression

Choose the correct answer from the options given below :

• A. A, B, E only
• B. A, C, D only
• C. C, D, E only
• D. B, C, E only

Hint:

To remember the difference: Regression = Real numbers (continuous). Classification = Categories (discrete).

Answer 1

The Correct Option is C

Concept:
• Supervised learning is divided into Classification (discrete) and Regression (continuous).
• Unsupervised learning deals with unlabeled data (Clustering).
• Reinforcement learning involves an agent learning through environmental feedback.

Step 1: Evaluate Regression and Classification (A, B)
Regression models predict numerical/continuous values (e.g., house prices). Classification models predict discrete labels/categories (e.g., spam vs. not spam). Statement A and B have their definitions swapped, so both are incorrect.

Step 2: Evaluate Clustering (C)
Clustering is the task of grouping a set of objects such that objects in the same group are more similar to each other than to those in other groups. Since this is done without target labels, it is an unsupervised task. Statement C is correct.

Step 3: Evaluate Reinforcement Learning (D)
In reinforcement learning, an agent learns to behave in an environment by performing actions and seeing the results as rewards or penalties. This is the core mechanism of the paradigm. Statement D is correct.

Step 4: Evaluate Decision Trees (E)
Decision trees can handle both categorical targets (Classification trees) and continuous targets (Regression trees). This versatility is a key feature of the CART (Classification and Regression Trees) algorithm. Statement E is correct.